© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 130280
    Prev
    Next
    INDEX
    Explanations

    websites and blogs introducing content

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/gemma-4-saes/gemma-4-31b
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    燗
    -0.07
     किससे
    -0.06
     Wikiseite
    -0.06
     miệng
    -0.06
     Yukawa
    -0.06
     আবারও
    -0.06
    Notably
    -0.06
    高い
    -0.06
     கடுமையான
    -0.06
     повышен
    -0.06
    POSITIVE LOGITS
     your
    0.08
     you
    0.08
    你就
    0.07
    ทั้งหมด
    0.06
     вашего
    0.06
    全都
    0.06
    していきます
    0.06
     youll
    0.06
     вашей
    0.06
    ……
    0.06
    Activations Density 0.028%

    No Known Activations